© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 120
    Prev
    Next
    INDEX
    Explanations

    in + context noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    お金
    0.48
    お
    0.47
    我
    0.46
    স
    0.46
    我和
    0.45
    ки
    0.45
     rask
    0.44
    おい
    0.43
    Ϝ
    0.43
     jasa
    0.43
    POSITIVE LOGITS
     diante
    0.39
     cuanto
    0.38
     السابق
    0.36
     contender
    0.35
    preprint
    0.34
    bumptech
    0.34
     السعودية
    0.34
     στα
    0.34
    ㅗ
    0.33
    द्धांत
    0.33
    Activations Density 0.453%

    No Known Activations